-
# Qwen1.5-MoE Support
With the increasing attention on mixture-of-experts (MoE) models, especially following the advancements heralded by Mixtral, I propose considering the integration of the Qwen1.5…
-
### 如上述文字
自定义模型0.5B 是json文件这么写不对吗?请指教,json无法解析
![image](https://github.com/xorbitsai/inference/assets/125621025/873e5d80-2f66-45f3-b234-97e729b81b32)
![image](https://github.com/xorbitsai/infer…
-
-
使用 tools 调用"glm4-chat-1m"模型。报错如下错误。
openai.BadRequestError: Error code: 400 - {'detail': "Only ['chatglm3', 'gorilla-openfunctions-v1', 'qwen-chat', 'qwen1.5-chat'] support tool calls"}
-
环境配置
A 环境 cuda12.1 v0.2.0
B 环境 cuda11.8 v0.1.13
硬件
A800单卡测试
模型 qwen14B
单卡加载 int8推理 环境变量如下配置
export CUDA_VISIBLE_DEVICES=1
export MODEL_TYPE=qwen_2
export ACT_TYPE=BF16
export WEIGHT_TYPE=…
-
大佬能不能出一个最简化的 全量SFT QWEN1.5的 代码呀。
-
# HuggingFace
https://huggingface.co/Qwen/Qwen1.5-72B-Chat
-
### 🚀 The feature, motivation and pitch
we had trained a lot of lora with qwen-7b ,if vllm support qwen-7b not only qwen1.5 ,that will be better,thanks
### Alternatives
_No response_
### Additiona…
-
【现象】
qwen1.5-14B-Chat模型在解码时报UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 1: unexpected end of data。
【描述】
模型输入是:假设f(x)=x,那么f(x)1到2的积分是多少。模型输出的tokenId包含11995、18137,这两个tokenId会…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/tencentmusic/supersonic/issues?q=is%3Aissue) and found no similar issues.
### Description
大模型输出的sql不稳定,时间条件不满足promp…